CN107240185B - A kind of crown word number identification method, device, equipment and storage medium - Google Patents
A kind of crown word number identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN107240185B CN107240185B CN201710487812.7A CN201710487812A CN107240185B CN 107240185 B CN107240185 B CN 107240185B CN 201710487812 A CN201710487812 A CN 201710487812A CN 107240185 B CN107240185 B CN 107240185B
- Authority
- CN
- China
- Prior art keywords
- connected domain
- word number
- crown word
- target
- topography
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Discrimination (AREA)
Abstract
The embodiment of the invention discloses a kind of crown word number identification method, device, equipment and storage mediums.Recognition methods includes pre-processing to crown word number region, generates topography corresponding with respective character each in the crown word number region；Determine the connected domain quantity for including in each topography；If the connected domain quantity for including in target topography is greater than 1, in all connected domains of the target topography, target connected domain corresponding with crown word number is identified；Crown word number identification is carried out to the target connected domain corresponding with crown word number.The technical solution of the present embodiment, by when the connected domain quantity for including in target locally chain code to be identified is greater than 1, then in all connected domains of target topography, target connected domain corresponding with crown word number is identified, and crown word number identification is carried out to target connected domain corresponding with crown word number.Solve the problems, such as it is lower to serial number recognition accuracy in the prior art, to accurately identify the serial number in banknote.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of crown word number identification method, device, equipment
And storage medium.
Background technique
With being gradually increased for note-issue's amount, the counterfeit protection measures of RMB also enhance therewith.Since crown word number can be made
For a decision factor for determining the RMB true and false, it is therefore widely used in the scheme of RMB truth identification.Every people
The people carry out unique identification by crown word number, and passing through identification and carrying out verifying to the crown word number of identification can determine the true and false of crown word number.
Have in the prior art by carrying out lateral and vertical projecting integral to binary image and positions and divide prefix
Number, and then identify crown word number.
However this method is lower to crown word number recognition accuracy, it is therefore necessary to release the new technical solution of one kind to solve
Above-mentioned technical problem.
Summary of the invention
The present invention provides a kind of crown word number identification method, device, equipment and storage medium, is identified with improving to crown word number
Accuracy.
In a first aspect, the embodiment of the invention provides a kind of crown word number identification methods, this method comprises:
Crown word number region is pre-processed, part corresponding with respective character each in the crown word number region is generated
Image；
Determine the connected domain quantity for including in each topography；
If the connected domain quantity for including in target topography is greater than 1, in all companies of the target topography
In logical domain, target connected domain corresponding with crown word number is identified；
Crown word number identification is carried out to the target connected domain corresponding with crown word number.
Second aspect, the embodiment of the invention also provides a kind of crown word number identification device, which includes:
Topography's generation module, it is each in generation and the crown word number region for being pre-processed to crown word number region
The corresponding topography of respective character；
Connected domain quantity determining module, for determining the connected domain quantity for including in each topography；
Target connected domain identification module, if the connected domain quantity for including in target topography is greater than 1, in institute
It states in all connected domains of target topography, identifies target connected domain corresponding with crown word number；
Crown word number identification module, for carrying out crown word number identification to the target connected domain corresponding with crown word number.
The third aspect, the embodiment of the invention also provides a kind of equipment, the equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes crown word number identification method as described in the embodiments of the present invention.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the storage medium is deposited thereon
Computer program is contained, which realizes crown word number identification method as described in the embodiments of the present invention when being executed by processor.
The technical solution of the present embodiment, by when the connected domain quantity for including in target locally chain code to be identified be greater than 1 when,
Then in all connected domains of target topography, identify target connected domain corresponding with crown word number, and to crown word number pair
The target connected domain answered carries out crown word number identification.Solve the problems, such as it is lower to serial number recognition accuracy in the prior art, from
And accurately identify the serial number in banknote.
Detailed description of the invention
Fig. 1 is one of embodiment of the present invention one crown word number identification method flow diagram；
Fig. 2 is one of embodiment of the present invention two crown word number identification method flow diagram；
Fig. 3 is one of embodiment of the present invention three crown word number identification device structural schematic diagram；
Fig. 4 is the structural schematic diagram of one of the embodiment of the present invention four crown word number identification equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of crown word number identification method flow chart that the embodiment of the present invention one provides, which can
To be suitable for the case where identifying to the crown word number of bank note, this method can be executed by crown word number identification device, the device
It can be realized, and generally be can integrate in the various gold for needing to carry out forge or true or paper money identification by the way of software and/or hardware
Melt in equipment, for example, ATM machine or cash inspecting machine etc., the method for the present embodiment specifically comprises the following steps:
S110, crown word number region is pre-processed, generation is respectively corresponded with each respective character in the crown word number region
Topography.
Wherein, crown word number region is the region in bank note where serial number, can be located at the lower left corner part of bank note.Show
Example property, the RMB of 100 yuan of face amounts its having a size of 165*77mm, using 1mm as coordinate system unit, crown word number region for (5,
15) rectangular area of (45,15) (45,20) (5,20) composition.
Serial number in crown word number region, can be by Arabic numerals and word for recording emission of banknotes sequence
Mother's composition.
Optionally, the pretreatment operation is used to crown word number region segmentation distinguishing institute for multiple independent prefix sign characters
The zonule at place, can there are many methods to realize, for example, since the distance between multiple independent crown word numbers determine, and crown word number area
Domain determines, crown word number region can be divided into the region of quantity identical as independent crown word number according to preset region；Again
For example, binary conversion treatment can be carried out to crown word number, and according in binary conversion treatment picture in prefix sign character region
The difference of the value of pixel in pixel and white space, is split to obtain each respective character and respectively corresponds to crown word number region
Topography.
It include at least one prefix sign character in the topography, it can be by identifying that it is each only that topography obtains
It signs an agreement, a contract, a receipt, etc. symbol.Preferably, character number is identical in the number with crown word number of topography.
S120, the connected domain quantity for including in each topography is determined.
Wherein, connected domain is can be in topography by the sets of adjacent pixels pixel set with same pixel value
The character outline being completely closed.The recognition methods of connected domain includes the labeling method based on stroke, the labeling method based on profile
With the recognition methods based on chain code.
It can be by determining connected domain quantity based on the recognition methods of connected domain chain code in the present embodiment.In topography
Connected domain is corresponding with the chain code being completely closed, therefore connected domain quantity can pass through the part chain code to be identified in topography
It determines, i.e., connected domain quantity is corresponding with the quantity of part chain code to be identified.
Illustratively, part chain code to be identified is used to describe the curved boundary pixel of respective character in topography, leads to
It is often used the starting point coordinate and edge direction of curve.Part chain code to be identified can be according to central pixel point adjacent direction
Several differences is divided by 4 connection chain codes and 8 connection two kinds of coding modes of chain code.Specifically, the abutment points of 4 connection chain codes have 4
It is a, respectively in the up, down, left and right of central point.8 connection chain codes increase 4 tilted directions than 4 connection chain codes, because any one
There are 8 abutment points around a pixel.
Preferably, part chain code to be identified includes: 8 connection chain codes.The advantages of this arrangement are as follows 8 connection chain codes
It is consistent with the actual conditions of pixel for forming respective character in topography, makes to describe central pixel point and be adjacent letter a little
It is more accurate to cease.
Optionally, the topography includes at least one part chain code to be identified, specifically, including in topography
The quantity of part chain code to be identified is more, and the accuracy rate identified to respective character in topography is higher, correspondingly, identification process
Middle elapsed time is more long, therefore can comprehensively consider to the accuracy rate of the identification time and identification to be consumed and then part is arranged
The quantity of chain code to be identified.
If the connected domain quantity for including in S130, target topography is greater than 1, in the institute of the target topography
Have in connected domain, identifies target connected domain corresponding with crown word number.
It wherein, may include at least one connected domain chain code in target topography；Target connected domain can be in bank note
The pixel chain code for being stained image in crown word number region, in the present embodiment, the detection method of connected domain chain code includes being based on
The method of region growing and method based on Contour extraction.
When the quantity of the connected domain chain code detected, i.e. connected domain quantity is greater than 1, then it represents that includes in current topography
At least one dirty character, at this time, it may be necessary to by whole connected domain chain codes standard chain with pre-stored standard crown word number one by one
Code feature Fuzzy matching obtains character match similarity, and according to non-in character match similarity removal part identification chain code
Crown word number chain code (that is, corresponding to the chain code being stained), obtains crown word number chain code.
Alternatively, can be with the standard chain code feature of standard crown word number according to the pre-stored data, application model identification side
Method identifies the connected domain, to improve the accuracy rate of chain code identification.
S140, crown word number identification is carried out to the target connected domain corresponding with crown word number.
To in the identification process of target connected domain corresponding with crown word number, it is stored in database in advance current embodiment require that utilizing
Character template target connected domain is precisely matched, and then obtain more accurate recognition result.
Optionally, the present embodiment carry out crown word number identification process in, can by S130 with character match similarity
Highest character as recognition result, the advantages of this arrangement are as follows, reduce the data processing generated in character recognition process
Amount, reduces job costs.
The technical solution of the present embodiment, by when the connected domain quantity for including in target locally chain code to be identified be greater than 1 when,
Then in all connected domains of target topography, identify target connected domain corresponding with crown word number, and to crown word number pair
The target connected domain answered carries out crown word number identification.Solve the problems, such as it is lower to serial number recognition accuracy in the prior art, from
And accurately identify the serial number in banknote.
Embodiment two
Fig. 2 is a kind of crown word number identification method flow chart provided by Embodiment 2 of the present invention, and the present embodiment is in above-mentioned each reality
On the basis of applying example, the non-crown word number chain for including in target chain code to be identified is identified preferably by application model recognition methods
Code, specifically:
S210, crown word number region is pre-processed, generation is respectively corresponded with each respective character in the crown word number region
Topography.
S220, the connected domain quantity for including in each topography is determined.
If the connected domain quantity for including in S230, target topography be greater than 1, according to and the target topography
In each connected domain to be measured image outline, calculate character feature corresponding with each connected domain to be measured, wherein character spy
Sign includes area, the chain code length of image outline, the width of the height of image outline and image outline, the image wheel of image outline
Wide depth-width ratio, at least one of.
Wherein, image outline can be detected by edge detection method, and carry out binaryzation and refinement to image outline
Processing.Character feature is calculated from the related information of image outline or image outline, may include image outline area,
At least one of in the width of the chain code length of image outline, the height of image outline and image outline.Wherein, image outline
Area can calculate function by preset contour area and be calculated, and the chain code length of image outline can pass through statistical picture
The corresponding chain code total number of profile obtains, and the height of image outline can be by calculating the highest point of image outline covering and minimum
The difference of the coordinate of point is got, and width can be obtained by the difference of the left end point and right end point that calculate image outline covering
It takes.
S240, using mode identification method, character feature corresponding with each connected domain to be measured and standard are preced with
The standard feature of font size is compared.
The working principle of mode identification method are as follows: to various forms of (numerical value, the text sums of characterization things or phenomenon
Logical relation) information handled and analyzed, with the process that things or phenomenon are described, recognize, classify and are explained, into
And complete to target object automatically process and interpretation.Optionally, the mode identification method includes calculating closest to rule classification
Method, decision Tree algorithms and linear classification algorithm.
Preferably, the comparison priority of character feature is chain code length, the height of image outline and the image of image outline
The width of profile, the depth-width ratio of image outline, image outline area.The advantages of this arrangement are as follows can be according to character spy
The priority match of sign, and then workload is reduced, improve working efficiency.
Optionally, those skilled in the art can compare chain code feature according to use pattern recognition methods and obtain with standard chain code
The accuracy of the comparing result and comparing result that arrive sets a preset value, corresponding with target connected domain to be measured to judge
Whether chain code feature matches with the standard chain code feature of standard crown word number, and then improves the accuracy of chain code identification.
If the standard feature of S250, character feature corresponding with target connected domain to be measured and standard crown word number mismatches,
Connected domain corresponding with target connected domain to be measured is then identified as dirty character connected domain.
Wherein, standard crown word number may include 10 bit digitals and 26 capitalizations, and standard feature then includes from each mark
The chain code length of the image outline extracted in quasi- crown word number, the width of the height of image outline and image outline, image outline
Area.
Illustratively, when described when the corresponding chain code length of target connected domain to be measured is greater than in prefix sign character template most
Big chain code length or when being less than minimal chain code length, then be identified as non-crown word number chain code for target connected domain chain code to be measured,
That is dirty character connected domain.
S260, it is identified according to the connected domain for including in the target topography, and in the target topography
Dirty character connected domain out determines the target connected domain.
Otherwise current operation chain code is identified as crown word number chain code, and to the subchain code in the current operational chain code respectively with
Chain code feature in database is compared, and then obtains the corresponding prefix sign character of current operation chain code.
S270, crown word number identification is carried out to the target connected domain corresponding with crown word number.
Further, when the connected domain quantity for including in target locally chain code to be identified be not more than 1, then illustrate target part
Chain code to be identified does not include non-crown word number chain code, and can be directly to target locally chain code identification to be identified, and then carries out prefix
Number identification.
The technical solution of the present embodiment is wrapped by being identified in the target chain code to be identified using application model recognition methods
The non-crown word number chain code included is further ensured that the automation of non-crown word number chain code recognition methods, meanwhile, improve recognition result
Accuracy rate.
Embodiment three
Fig. 3 show a kind of crown word number identification device structural schematic diagram of the offer of the embodiment of the present invention three, as shown in figure 3,
The crown word number identification device includes: topography's generation module 310, connected domain quantity determining module 320, the identification of target connected domain
Module 330 and crown word number identification module 340.
Wherein, topography's generation module 310 generates and the crown word number for pre-processing to crown word number region
The corresponding topography of each respective character in region；
Connected domain quantity determining module 320, for determining the connected domain quantity for including in each topography；
Target connected domain identification module 330, if the connected domain quantity for including in target topography is greater than 1,
In all connected domains of the target topography, target connected domain corresponding with crown word number is identified；
Crown word number identification module 340, for carrying out crown word number identification to the target connected domain corresponding with crown word number.
The technical solution of the present embodiment, by when the connected domain quantity for including in target locally chain code to be identified be greater than 1 when,
Then in all connected domains of target topography, identify target connected domain corresponding with crown word number, and to crown word number pair
The target connected domain answered carries out crown word number identification.Solve the problems, such as it is lower to serial number recognition accuracy in the prior art, from
And accurately identify the serial number in banknote.
On the basis of the various embodiments described above, the target connected domain identification module 330 includes:
Character feature acquiring unit, for according to and each connected domain to be measured in the target topography image outline,
Calculate character feature corresponding with each connected domain to be measured, wherein character feature includes the area of image outline, image
At least one of in the width of the chain code length of profile, the height of image outline and image outline；
Feature comparing unit will character corresponding with each connected domain to be measured for utilizing mode identification method
Feature is compared with the standard feature of standard crown word number；
Dirty character judging unit, if for character feature corresponding with target connected domain to be measured and standard crown word number
Standard feature mismatches, then connected domain corresponding with target connected domain to be measured is identified as dirty character connected domain；
Target connected domain removes top unit, for according to the connected domain for including in the target topography, and described
The dirty character connected domain identified in target topography determines the target connected domain.
On the basis of the various embodiments described above, the comparison priority of character feature is the chain code length of image outline, image
The height and the width of image outline of profile, the depth-width ratio of image outline, image outline area.
On the basis of the various embodiments described above, the mode identification method includes closest to rule classification algorithm, decision tree
Algorithm and linear classification algorithm.
Crown word number identification device provided by the embodiment of the present invention can be used for executing hat provided by the embodiment of the present invention
Font size recognition methods has corresponding function and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to
The crown word number identification method that any embodiment of that present invention provides.
Example IV
The embodiment of the invention provides a kind of equipment, which includes processor 410, memory 420, input unit 430
With output device 440；The quantity of processor 410 can be one or more, in Fig. 4 by taking a processor 410 as an example；In equipment
Processor 410, memory 420, input unit 430 can connect with output device 440 by bus or other modes.
Memory 410 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, such as the corresponding program instruction of one of embodiment of the present invention crown word number identification method.Processor 410 passes through fortune
Software program, instruction and the module that row is stored in memory 420, thereby executing the various function application and data of equipment
Processing, that is, realize a kind of above-mentioned crown word number identification method.
Namely: the processor is realized when executing described program: being pre-processed, is generated and the hat to crown word number region
The corresponding topography of each respective character in font size region；Determine the connected domain quantity for including in each topography；If
The connected domain quantity for including in target topography is greater than 1, then in all connected domains of the target topography, identifies
Target connected domain corresponding with crown word number；Crown word number identification is carried out to the target connected domain corresponding with crown word number.
Memory 420 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function；Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 420 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 420 can be into one
Step includes the memory remotely located relative to processor 410, these remote memories can pass through network connection to equipment.On
The example for stating network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 430 can be used for receiving the number or character information of input, and generate with the user setting of equipment with
And the related key signals input of function control.Output device 440 may include that display screen etc. shows equipment.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction is used to execute a kind of crown word number identification method when being executed by computer processor, this method comprises:
Crown word number region is pre-processed, part corresponding with respective character each in the crown word number region is generated
Image；
Determine the connected domain quantity for including in each topography；
If the connected domain quantity for including in target topography is greater than 1, in all companies of the target topography
In logical domain, target connected domain corresponding with crown word number is identified；
Crown word number identification is carried out to the target connected domain corresponding with crown word number.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed crown word number provided by any embodiment of the invention and knows
Relevant operation in other method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, included each unit and module are only according to function in the embodiment of above-mentioned searcher
Energy logic is divided, but is not limited to the above division, as long as corresponding functions can be realized；In addition, each function
The specific name of energy unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (8)
1. a kind of crown word number identification method characterized by comprising
Crown word number region is pre-processed, target part corresponding with respective character each in the crown word number region is generated
Image；
Determine the connected domain quantity for including in each target topography；
If the connected domain quantity for including in target topography is greater than 1, in all connected domains of the target topography
In, identify target connected domain corresponding with crown word number；
Crown word number identification is carried out to the target connected domain corresponding with crown word number；
Wherein, in all connected domains of the target topography, identify that target connected domain corresponding with crown word number includes:
According to the image outline with each connected domain to be measured in the target topography, calculating is respectively corresponded with each connected domain to be measured
Character feature, wherein character feature includes the area of image outline, the chain code length of image outline, the height of image outline
With at least one in the width of image outline；
Using mode identification method, by the standard of corresponding with each connected domain to be measured character feature and standard crown word number
Feature is compared；
If the standard feature of character feature corresponding with target connected domain to be measured and standard crown word number mismatches, will be with target
The corresponding connected domain of connected domain to be measured is identified as dirty character connected domain；
According to the connected domain for including in the target topography, and that identifies in the target topography be stained word
Connected domain is accorded with, determines the target connected domain.
2. crown word number identification method according to claim 1, which is characterized in that
The comparison priority of character feature be the chain code length of image outline, the height of image outline and image outline width,
The area of the depth-width ratio of image outline, image outline.
3. -2 described in any item crown word number identification methods according to claim 1, it is characterised in that:
The mode identification method includes Nearest Neighbor Method sorting algorithm, decision Tree algorithms and linear classification algorithm.
4. a kind of crown word number identification device characterized by comprising
Target topography generation module, it is each in generation and the crown word number region for being pre-processed to crown word number region
The corresponding target topography of respective character；
Connected domain quantity determining module, for determining the connected domain quantity for including in each target topography；
Target connected domain identification module, if the connected domain quantity for including in target topography is greater than 1, in the mesh
In all connected domains for marking topography, target connected domain corresponding with crown word number is identified；
Crown word number identification module, for carrying out crown word number identification to the target connected domain corresponding with crown word number；
Wherein, the target connected domain identification module includes: character feature acquiring unit, for basis and the target Local map
The image outline of each connected domain to be measured as in calculates character feature corresponding with each connected domain to be measured, wherein character
Feature includes in the width of the area of image outline, the chain code length of image outline, the height of image outline and image outline
At least one of；
Feature comparing unit will character feature corresponding with each connected domain to be measured for utilizing mode identification method
It is compared with the standard feature of standard crown word number；
Dirty character judging unit, if the standard for corresponding with target connected domain to be measured character feature and standard crown word number
Feature mismatches, then connected domain corresponding with target connected domain to be measured is identified as dirty character connected domain；
Target connected domain removes top unit, for according to the connected domain for including in the target topography, and in the target
The dirty character connected domain identified in topography determines the target connected domain.
5. crown word number identification device according to claim 4, which is characterized in that
The comparison priority of character feature be the chain code length of image outline, the height of image outline and image outline width,
The area of the depth-width ratio of image outline, image outline.
6. according to any crown word number identification device of claim 4-5, it is characterised in that:
The mode identification method includes closest to rule classification algorithm, decision Tree algorithms and linear classification algorithm.
7. a kind of terminal, which is characterized in that the terminal includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as crown word number identification method as claimed in any one of claims 1-3.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
Such as crown word number identification method as claimed in any one of claims 1-3 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710487812.7A CN107240185B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710487812.7A CN107240185B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107240185A CN107240185A (en) | 2017-10-10 |
| CN107240185B true CN107240185B (en) | 2019-09-20 |
Family
ID=59987282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710487812.7A Active CN107240185B (en) | 2017-06-23 | 2017-06-23 | A kind of crown word number identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107240185B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895191B (en) | 2017-10-30 | 2022-02-22 | 上海寒武纪信息科技有限公司 | Information processing method and related product |
| US20210133854A1 (en) | 2018-09-13 | 2021-05-06 | Shanghai Cambricon Information Technology Co., Ltd. | Information processing method and terminal device |
| CN114169352A (en) * | 2021-10-27 | 2022-03-11 | 珠海格力智能装备有限公司 | Bar code information identification method and electronic equipment |
| CN116486418B (en) * | 2023-06-19 | 2023-10-03 | 恒银金融科技股份有限公司 | Method and device for generating banknote crown word number image |
| CN117671849B (en) * | 2023-12-14 | 2024-05-14 | 浙江南星科技有限公司 | Vertical image scanning banknote counter adopting banknote sliding structure |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617674A (en) * | 2013-10-23 | 2014-03-05 | 东方通信股份有限公司 | Bill discharging machine core capable of identifying crown word number, and crown word number identification method thereof |
| CN104268505A (en) * | 2014-09-12 | 2015-01-07 | 河海大学常州校区 | Automatic cloth defect point detection and recognition device and method based on machine vision |
| CN105261109A (en) * | 2015-07-24 | 2016-01-20 | 广州广电运通金融电子股份有限公司 | Identification method of prefix letter of banknote |
| CN105303189A (en) * | 2014-07-29 | 2016-02-03 | 阿里巴巴集团控股有限公司 | Method and device for detecting specific identification image in predetermined area |
| CN105336035A (en) * | 2015-10-28 | 2016-02-17 | 深圳怡化电脑股份有限公司 | Smudged serial number image classification method and system |
| CN105373794A (en) * | 2015-12-14 | 2016-03-02 | 河北工业大学 | Vehicle license plate recognition method |
| CN105389883A (en) * | 2015-11-04 | 2016-03-09 | 东方通信股份有限公司 | Banknote prefix number identification method for currency detector |
| CN106709484A (en) * | 2015-11-13 | 2017-05-24 | 国网吉林省电力有限公司检修公司 | Number identification method of digital instrument |
| CN105261110B (en) * | 2015-10-26 | 2018-04-06 | 江苏国光信息产业股份有限公司 | A kind of efficiently DSP paper money number recognition methods |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100579B (en) * | 2014-05-09 | 2018-12-07 | 华为技术有限公司 | A kind of acquiring and processing method and relevant apparatus of image data |
-
2017
- 2017-06-23 CN CN201710487812.7A patent/CN107240185B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617674A (en) * | 2013-10-23 | 2014-03-05 | 东方通信股份有限公司 | Bill discharging machine core capable of identifying crown word number, and crown word number identification method thereof |
| CN105303189A (en) * | 2014-07-29 | 2016-02-03 | 阿里巴巴集团控股有限公司 | Method and device for detecting specific identification image in predetermined area |
| CN104268505A (en) * | 2014-09-12 | 2015-01-07 | 河海大学常州校区 | Automatic cloth defect point detection and recognition device and method based on machine vision |
| CN105261109A (en) * | 2015-07-24 | 2016-01-20 | 广州广电运通金融电子股份有限公司 | Identification method of prefix letter of banknote |
| CN105261110B (en) * | 2015-10-26 | 2018-04-06 | 江苏国光信息产业股份有限公司 | A kind of efficiently DSP paper money number recognition methods |
| CN105336035A (en) * | 2015-10-28 | 2016-02-17 | 深圳怡化电脑股份有限公司 | Smudged serial number image classification method and system |
| CN105389883A (en) * | 2015-11-04 | 2016-03-09 | 东方通信股份有限公司 | Banknote prefix number identification method for currency detector |
| CN106709484A (en) * | 2015-11-13 | 2017-05-24 | 国网吉林省电力有限公司检修公司 | Number identification method of digital instrument |
| CN105373794A (en) * | 2015-12-14 | 2016-03-02 | 河北工业大学 | Vehicle license plate recognition method |
Non-Patent Citations (1)
| Title |
|---|
| "纸币冠字号预处理及组合特征识别方法";梁杨;《计算机工程与设计》;20150816;第36卷(第8期);第2223-2228页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107240185A (en) | 2017-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107240185B (en) | A kind of crown word number identification method, device, equipment and storage medium | |
| CN106156766B (en) | Method and device for generating text line classifier | |
| CN107194400B (en) | Financial reimbursement full ticket image recognition processing method | |
| US8494273B2 (en) | Adaptive optical character recognition on a document with distorted characters | |
| CN110619274A (en) | Identity verification method and device based on seal and signature and computer equipment | |
| US10643094B2 (en) | Method for line and word segmentation for handwritten text images | |
| US9965695B1 (en) | Document image binarization method based on content type separation | |
| CN109685065B (en) | Layout analysis method and system for automatically classifying test paper contents | |
| Lacerda et al. | Segmentation of connected handwritten digits using Self-Organizing Maps | |
| Piekarczyk | Hierarchical random graph model for off-line handwritten signatures recognition | |
| CN108268641A (en) | Invoice information recognition methods and invoice information identification device, equipment and storage medium | |
| Asra et al. | Human behavior recognition based on hand written cursives by SVM classifier | |
| AbdelRaouf et al. | Arabic character recognition using a Haar cascade classifier approach (HCC) | |
| Farulla et al. | A fuzzy approach to segment touching characters | |
| CN112232336A (en) | Certificate identification method, device, equipment and storage medium | |
| CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
| CN104463084A (en) | Off-line handwritten signature recognition method based on non-negative matrix factorization | |
| Parui et al. | Offline handwritten devanagari word recognition: An hmm based approach | |
| Suleyman et al. | An adaptive threshold algorithm for offline Uyghur handwritten text line segmentation | |
| Sathya Narayanan et al. | RETRACTED ARTICLE: An efficient recognition system for preserving ancient historical documents of English characters | |
| CN111199240A (en) | Training method of bank card identification model, and bank card identification method and device | |
| Sarkar et al. | Suppression of non-text components in handwritten document images | |
| Chandra et al. | Verification of static signature pattern based on random subspace, REP tree and bagging | |
| US20180225508A1 (en) | Detecting document objects | |
| CN107331030B (en) | A kind of crown word number identification method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |